Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    events, threats, or disasters that are impending or imminent

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    words and phrases indicating imminent threats or disasters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.05
    1:0.03
    2:0.09
    3:0.12
    4:0.16
    5:0.07
    6:0.02
    7:0.03
    8:0.14
    9:0.15
    10:0.05
    11:0.02
    Negative Logits
    verbs
    -1.54
     knit
    -1.23
     curiously
    -1.23
     Tik
    -1.21
    isters
    -1.20
    redited
    -1.20
     Mahjong
    -1.16
    BN
    -1.16
    eah
    -1.14
    odium
    -1.14
    POSITIVE LOGITS
    arenthood
    1.90
     imminent
    1.50
    rosso
    1.42
    llah
    1.37
    irements
    1.37
    comings
    1.36
     consequences
    1.35
    LEASE
    1.34
    ptions
    1.32
     impending
    1.32
    Act Density 0.005%

    No Known Activations